© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93655
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.01
     pleaſure
    -0.96
     Diſ
    -0.94
     ſtate
    -0.93
     Chriftian
    -0.93
     preſent
    -0.92
     reaſon
    -0.92
     myſelf
    -0.91
     Houſe
    -0.90
     uſe
    -0.88
    POSITIVE LOGITS
    __":
    0.50
    0
    0.47
    1
    0.44
    __':
    0.41
     OnInit
    0.41
    <em>
    0.37
    <i>
    0.35
    @
    0.35
    <u>
    0.35
    </em>
    0.34
    Activations Density 0.002%

    No Known Activations